python 爬虫(头像)

import re
import os
import requests

global i
i = 0


def get_one_page(url):
    response = requests.get(url)
    response.encoding = 'utf-8'
    html = response.text
    return html


def get_urls(html):
    pattern = re.compile('href="(/touxiang/qinglv/20\d+/\d+\.html)"', re.S)
    urls = re.findall(pattern, html)
    return urls


def get_pic_url(html):
    pattern = re.compile('href="(//img\d\.woyaogexing\.com/20\d\d.*?\.jpeg)"', re.S)
    pic_urls = re.findall(pattern, html)
    return pic_urls


def save_pic(url, pic_path):
    global i
    if not os.path.exists(pic_path):
        os.mkdir(pic_path)
    with open(os.path.join(pic_path, str(i) + '.jpg'), 'wb') as f:
        # f.write(requests.get(url).content)
      print(url)
    i += 1


def main():
    html = get_one_page('https://www.woyaogexing.com/touxiang/qinglv/new/')
    urls = get_urls(html)
    for url in urls:
        sub_html = get_one_page('https://www.woyaogexing.com' + url)
        pic_urls = get_pic_url(sub_html)
        for pic_url in pic_urls:
            save_pic('http:' + pic_url, 'D:\\test\\')


if __name__ == '__main__':
    main()

原文章